Assessment of remotely sensed inventories for land cover classification of public grasslands in Manitoba, Canada
Bibliographic record
Abstract
Abstract Land cover classification is one of the most common applications of remote sensing and is used for developing and modifying land management policies on agricultural landscapes to achieve conservation and economic goals, such as reducing grassland degradation and improving livestock and crop production. In this study, the grassland classification of the crown lands (public grasslands in Canada) from a newly developed remotely sensed dataset in the Prairie Province of Manitoba (i.e., the Manitoba Grassland Inventory, MGI) was assessed in terms of accuracy by comparison to non‐spatial government records. The analysis consisted of (i) converting non‐spatial records from the provincial crown land database to spatially‐defined parcels by performing parcel delineations using geographic information system (GIS) and R programming tools, (ii) summarising the MGI classification at the same spatial scale, and (iii) comparing the agreement between MGI and the crown land database. The most common land cover types identified were: forest (30%) and shrubland (25%), followed by native (10%) and tame (9%) grasslands. However, the class agreements between woody (i.e., forests and shrublands) and grassy (i.e., native and tame grasslands) vegetation classes were low between these datasets because of their spectral similarities. Based on these results, we suggest additional refinements on both sensor and ground data to improve the classification agreement between these datasets. This study is one of the first attempts to compare ground‐collected government records against a remotely sensed product in Manitoba.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.006 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.000 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".